Ideogram

• Generation status changedWatches the status of one existing generation by its ID. The first successful poll establishes a baseline; later changes start the workflow. Polling follows your workspace plan.

• Generate ideogram 4 5Generate images with Ideogram 4.5 from a natural-language or structured JSON prompt. Optionally upload source images as `images` using `multipart/form-data` to edit them with the prompt. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Generate ideogram 4Generate images with Ideogram 4.0 from a natural-language or structured JSON prompt. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Generate ideogram 4 transparentGenerate images on a transparent background with Ideogram 4.0, delivered as PNGs with alpha. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Generate ideogram 3Generate images from a text prompt with Ideogram 3.0. Optional style controls include style codes, a style preset, a color palette, and style references (uploaded `style_reference_images`). Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Generate ideogram 3 transparentGenerate images on a transparent background with Ideogram 3.0, delivered as PNGs with alpha. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Generate ideogram 2aGenerate images from a text prompt with Ideogram 2a, a fast, lower-cost model. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Generate ideogram 2Generate images from a text prompt with Ideogram 2.0. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Get generationRetrieves the current status of an asynchronous generation, and its results once complete. Use the `generation_id` returned by any `/v2` endpoint that runs asynchronously: every video and tool endpoint, and any image endpoint called with `async` or a `webhook_url`. While the generation is `pending` or has `failed`, the response contains only `generation_id`, `status`, and `created` (plus `failure_reason` once failed). Once `status` is `completed`, the response includes `response_type` and `data`. Each `data` item carries an `object_type` that identifies its shape, so image and video results can be told apart. `usage_cost_usd_micros` reports the amount billed when the request uses variable usage-based pricing. Polling is rate limited per organization; a 429 response carries a `Retry-After` header with the number of seconds to wait.
• List invoicesReturns your organization's invoices with their line items ; the billing record your usage reports reconcile against. Amounts are decimal strings in the invoice's currency. Requires an API key whose owner is an organization admin. Keys owned by other members receive a 404.
• Get usageReturns your organization's billed API usage as dense time buckets of line items. Every line item carries the billed dollar amount; products billed per item also carry `billed_units` (unit, quantity, and unit price, where `quantity × unit_price = cost_total`). Usage-priced products (billed by metered provider usage) report `cost_total` only. Buckets cover the requested range completely ; a bucket with no line items means no billed usage in that window. Line items are unique per bucket on (`product`, `dimensions`, `api_key.id`, unit price). Usage billed without an API key (requests authenticated as a user session) is included with `api_key` absent, so totals always reconcile with your invoices. `product` and `endpoint` are stable identifiers safe to aggregate on; `description` is display text and may be reworded at any time. Usage data may lag live traffic by a few minutes, and responses may be cached briefly, so this endpoint is for rep
• Generate autoGenerate images with the model Ideogram picks as best suited to each request. Optionally upload source images as `images` using `multipart/form-data` to edit them with the prompt. Returns results directly by default; set `async` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Generate ideogram 4 custom modelGenerate images with a custom Ideogram 4.0 model that you or your organization can access, selected by `custom_model_uri`. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Generate ideogram 3 custom modelGenerate images with a custom Ideogram 3.0 model that you or your organization can access, selected by `custom_model_uri`. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Remix imageTransform an existing image with Ideogram 4.0, guided by a text prompt. Upload the source `image` using `multipart/form-data`. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Remix image v3Transform an existing image with Ideogram 3.0, guided by a text prompt. Upload the source `image` using `multipart/form-data`. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Inpaint imageRepaint the masked region of a source image with Ideogram 3.0, guided by a text prompt. Upload the source `image` and its `mask` using `multipart/form-data`. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Reframe imageExpand an image to a new Ideogram 3.0 resolution, keeping the source pixels in the center and filling the new area. Upload the source `image` using `multipart/form-data`. Returns results directly by default; set `async` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Upscale imageUpscale an image to 2x, 4x, or 8x its original resolution with a model Ideogram picks per request; the choice may change over time. Upload the source `image` using `multipart/form-data`. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Remove backgroundRemove the background from an image and return the foreground as a transparent PNG. Upload the source `image` using `multipart/form-data`. Returns the result directly by default; set `async` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`.
• Remove objectRemove a masked object from an image. Upload the source `image` and a `mask` of the same size using `multipart/form-data`. Returns a `generation_id`; poll `GET /v2/generations/{generation_id}` for the result.
• Describe imageDescribe an image as a structured `V4JsonPrompt` with Ideogram's 4.0 image captioner (a fine-tune of the Qwen3-VL vision-language model). Upload the image as `image` using `multipart/form-data`; the `json_prompt` is returned directly and can be passed to the `/v1/ideogram-v4/generate` endpoints.
• Precise edit imageEdit an image with Ideogram 4.5 and get the result back at that image's exact width and height. Upload the image as `image` using `multipart/form-data`, with optional `reference_images` and a `mask`. Returns results directly by default; set `async` or supply a `webhook_url` to get a `generation_id` and poll `GET /v2/generations/{generation_id}`. Editing the whole image is bounded by 4194304 pixels (the area of a 2048x2048 square), so a larger image comes back scaled down to fit: an 8192x8192 image returns as 2048x2048. To edit a 4K or 8K image at its full resolution, set `context_window` to confine the edit to one region, either `auto` together with a `mask`, or `y_min,x_min,y_max,x_max` to name the region yourself. Only that region changes, the rest of the image comes back unchanged, and the result keeps the image's own width and height at any input size. ```bash curl -X POST https://api.ideogram.ai/v2/image/precise-edit/ideogram-4-5 \
• Replace backgroundReplace the background of an image from a text prompt with Ideogram 3.0, keeping the automatically detected foreground subject; no mask is needed. Upload the source `image` using `multipart/form-data`. Returns a `generation_id`; poll `GET /v2/generations/{generation_id}` or supply a `webhook_url`.
• Generate svgGenerates SVG artwork from a prompt and optional image references.
• Vectorize imageConverts an image to SVG asynchronously.

No actions match that.